Tool reference · Errors, rules & self-improvement
memory_self_assess
Reports how experienced the memory thinks the agent is in given topics, with a confidence value and any known blind spots.
local stdio server read-only
When to use
- Before a task in an unfamiliar area, to decide how carefully to proceed.
- You want the list of known blind spots.
- You want the full self-model report (full_report: true).
Parameters
| Name | Type | Default | Description |
|---|---|---|---|
concepts | string[] | — | Domains/concepts to assess competency for |
full_report | boolean | false | Return full self-model report |
Example
Arguments
{
"concepts": [
"postgresql",
"kubernetes"
]
}Result shape
{
"level": 0.62,
"confidence": 0.45,
"blind_spots": [],
"note": "Moderate",
"domains_found": [
"postgresql"
]
}full_report returns competencies, competency_count, avg_level, trend_summary, blind_spots, blind_spot_count, user_model and user_model_entries.
Values are illustrative; the keys follow the server's handler. MCP clients receive the result as JSON text content.
Server description
The description the server sends to your agent in tools/list, captured from the v14.7.0 source:
Self-assessment: how competent am I in given domains? Shows level, confidence, blind spots.